Known Good MCP server
Which servers in the official MCP registry are Known Good's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namesh.knowngood/knowngoodverified in the MCP registry
The registry name sits under knowngood.sh. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools3
- Server calls itselfknowngood
- Server version1.9.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 25 ms.
- Its tools do every use case we checked: search for websites that AI agents can use; check a page for WebMCP support; read a site's agent-readiness test report.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- For "search for websites that AI agents can use", the likely first call is find_capability.
- For "check a page for WebMCP support", the likely first call is check_webmcp.
- For "read a site's agent-readiness test report", the likely first call is get_site_report.
- Parameters are untyped or undescribed in 1 of 3 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- What an agent can do with it3 of 3 use cases
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer267 ms
- Space in an agent's context≈ 864 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 94 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 1 of 3
What an agent can do with it
- can do · search for websites that AI agents can use
- can do · check a page for WebMCP support
- can do · read a site's agent-readiness test report
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
check_webmcpCheck a website LIVE for WebMCP tools, and where a browser is available whether any tool actually registers when the page runs. Returns one of: registered, declared_only, declared, not_declared, could_not_ask, or excluded when the site's…
find_capabilityFind websites where an agent can accomplish a task. Returns probe-verified agent-readiness signals, unverified apparent actions read from page content, the verification tier, how each site was found (it declared agent access, probe…
get_site_reportFetch Known Good's dated verification report for one listed website: which capabilities were tested, which passed, when it was probed, what an agent can apparently do there, and how the site was found: whether it declared agent access…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"knowngood": {
"type": "http",
"url": "https://knowngood.sh/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http knowngood https://knowngood.sh/mcpclaude.ai, ChatGPT and other clients: add https://knowngood.sh/mcp as a custom connector in the settings.
OpenAPI spec
4 paths, read 2026-10-20. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.